# Image Classification on CIFAR-10 + CIFAR-100 open-set noise (test)

Source: [Image Classification on CIFAR-10 + CIFAR-100 open-set noise (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-plus-cifar-100-open-set-noise-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:27:27.522Z

Evaluation of Image Classification performance on a combined test set consisting of CIFAR-10 and CIFAR-100 corrupted by open-set noise.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification |
| Dataset (including any stated split) | CIFAR-10 + CIFAR-100 open-set noise (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-plus-cifar-100-open-set-noise-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Avg Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-plus-cifar-100-open-set-noise-test.md?metric=Avg%20Accuracy>): Higher is better; unit: PERCENT.

- [Max Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-plus-cifar-100-open-set-noise-test.md?metric=Max%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| truncated Lq loss | 79.55 | Not recorded | 68fa651f1e209131cea088eb |
| Wang, et al. | 79.28 | Not recorded | 68fa651f1e209131cea088eb |
| MAE | 75.06 | Not recorded | 68fa651f1e209131cea088eb |
| Lq loss | 71.1 | Not recorded | 68fa651f1e209131cea088eb |
| Forward | 64.18 | Not recorded | 68fa651f1e209131cea088eb |
| CCE | 62.92 | Not recorded | 68fa651f1e209131cea088eb |

### truncated Lq loss

Accuracy: 79.55. Result ID: 698c9f100b614d12cff203a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

Recorded evaluation configuration: {"Noise rate (η)":"40%","Training epochs":"100"}. This record does not assert independent reproduction.

### Wang, et al.

Accuracy: 79.28. Result ID: 698c9f100b614d12cff2039d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035aa.md>)

Recorded evaluation configuration: {"Noise rate (η)":"40%","Training epochs":"100"}. This record does not assert independent reproduction.

### MAE

Accuracy: 75.06. Result ID: 698c9f100b614d12cff2039e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035aa.md>)

Recorded evaluation configuration: {"Noise rate (η)":"40%","Training epochs":"100"}. This record does not assert independent reproduction.

### Lq loss

Accuracy: 71.1. Result ID: 698c9f100b614d12cff2039f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

Recorded evaluation configuration: {"Noise rate (η)":"40%","Training epochs":"100"}. This record does not assert independent reproduction.

### Forward

Accuracy: 64.18. Result ID: 698c9f100b614d12cff2039c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035aa.md>)

Recorded evaluation configuration: {"Noise rate (η)":"40%","Training epochs":"100"}. This record does not assert independent reproduction.

### CCE

Accuracy: 62.92. Result ID: 698c9f100b614d12cff2039b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035aa.md>)

Recorded evaluation configuration: {"Noise rate (η)":"40%","Training epochs":"100"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.